Least mean squares learning in self-referential linear stochastic models

被引:13
作者
Barucci, E [1 ]
Landi, L
机构
[1] Univ Florence, DiMaDEFAS, I-50134 Florence, Italy
[2] Univ Florence, Dipartimento Sistemi & Informat, I-50134 Florence, Italy
关键词
least mean squares learning; rational expectations equilibria;
D O I
10.1016/S0165-1765(97)00202-4
中图分类号
F [经济];
学科分类号
02 ;
摘要
We analyze Self-Referential Linear Stochastic models under bounded rationality assuming that agents update their beliefs by means of the Least Mean Squares algorithm. This learning mechanism is less complex than Recursive Ordinary Least Squares learning and appears to be more plausible as a learning device for economic agents. We prove convergence of the learning mechanism, the convergence conditions are different from those required by Recursive Ordinary Least Squares learning. (C) 1997 Elsevier Science S.A.
引用
收藏
页码:313 / 317
页数:5
相关论文
共 6 条
[1]   RATIONAL EXPECTATIONS AND LEARNING FROM EXPERIENCE [J].
DECANIO, SJ .
QUARTERLY JOURNAL OF ECONOMICS, 1979, 93 (01) :47-57
[3]  
Evans GeorgeW., 1995, LEARNING RATIONALITY, P102
[4]   ANALYSIS OF RECURSIVE STOCHASTIC ALGORITHMS [J].
LJUNG, L .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1977, 22 (04) :551-575
[5]   CONVERGENCE OF LEAST-SQUARES LEARNING-MECHANISMS IN SELF-REFERENTIAL LINEAR STOCHASTIC-MODELS [J].
MARCET, A ;
SARGENT, TJ .
JOURNAL OF ECONOMIC THEORY, 1989, 48 (02) :337-368
[6]  
Widrow B., 1971, Adaptive Filters-Aspects of Network and System Theory, P563